Cross-modal Affinity-aligned Multimodal Learning Analytics for Predicting Student Collaboration Satisfaction in Game-Based Learning

ArXi:2605.16806v1 Announce Type: new Collaborative game-based learning environments offer rich opportunities for small-group knowledge construction, yet automatically predicting student collaboration satisfaction remains challenging. A critical barrier is modality degradation: in educational deployments, individual modalities such as eye gaze exhibit inconsistent informativeness across student cohorts, causing implicit attention-based fusion to produce brittle multimodal representations.